Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    age-matched comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    망
    -0.07
    Ů
    -0.07
     ?>"/>↵
    -0.07
    낡
    -0.07
    Ў
    -0.07
    -0.07
    -0.07
    لة
    -0.06
    mé
    -0.06
     groupId
    -0.06
    POSITIVE LOGITS
     реклам
    0.09
     THEN
    0.07
     Nico
    0.07
     stringify
    0.07
    前台
    0.07
     dvd
    0.07
    准时
    0.07
    客气
    0.07
     авиа
    0.07
    pick
    0.07
    Act Density 0.023%

    No Known Activations